Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction
Full Text: 2020.acl-main.452.pdfAutomatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. A good summary is characterized by language fluency and high information overlap with the source sentence. We model these two aspects in an unsupervised objective function, consisting of language modeling and semantic similarity metrics. We search for a high-scoring summary by discrete optimization. Our proposed method achieves a new state-of-the art for unsupervised sentence summarization according to ROUGE scores. Additionally, we demonstrate that the commonly reported ROUGE F1 metric is sensitive to summary length. Since this is unwillingly exploited in recent work, we emphasize that future evaluation should explicitly group summarization systems by output length brackets.
Citation
R. Schumann, L. Mou, Y. Lu, O. Vechtomova, K. Markert. "Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction". International Conference on Computational Linguistics and the Association for Computational Linguist, pp 5032–5042, July 2020.Keywords: | |
Category: | In Conference |
Web Links: | doi |
ACL |
BibTeX
@incollection{Schumann+al:ACL20, author = {Raphael Schumann and Lili Mou and Yao Lu and Olga Vechtomova and Katja Markert}, title = {Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction}, Pages = {5032–5042}, booktitle = {International Conference on Computational Linguistics and the Association for Computational Linguist}, year = 2020, }Last Updated: February 01, 2021
Submitted by Sabina P